Knowledge catalogue
recommended reading. i too am very done with people anthropomorphizing a bunch of matrices on a GPU cluster, especially if the same people do not give two fucks about actual human beings. More musings
arXiv:2605.25095v1 Announce Type: new Abstract: Autonomous driving stacks must pick one trajectory from a multi-modal candidate set; choosing by model confidence ignores safety, traffic-law, and comfo
arXiv:2605.24044v1 Announce Type: new Abstract: Robots deployed in dynamic environments must contend with environment-driven changes that reshape computation at runtime: new tasks may appear, preceden
arXiv:2602.19450v2 Announce Type: replace-cross Abstract: Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating sys
arXiv:2605.25673v1 Announce Type: cross Abstract: Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact
arXiv:2605.24357v1 Announce Type: new Abstract: In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the cr
arXiv:2602.01183v2 Announce Type: replace-cross Abstract: Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we add
arXiv:2605.24834v1 Announce Type: cross Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversar
Anima is a 2 billion parameter text-to-image model focused mainly on anime concepts and styles, but also capable of generating other non-photorealistic content. A Regional Condition Custom Node for An
arXiv:2605.25063v1 Announce Type: new Abstract: Reinforcement learning offers a promising approach for scan-order optimisation in laser additive manufacturing, where sequential scan decisions critical
arXiv:2605.24740v1 Announce Type: new Abstract: Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explore
arXiv:2605.25638v1 Announce Type: new Abstract: Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (dLLMs). We introd
arXiv:2605.25172v1 Announce Type: cross Abstract: This article is the rejoinder to ``The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review,'' to appear in the Journal
arXiv:2605.25508v1 Announce Type: new Abstract: At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed acro
arXiv:2409.02416v2 Announce Type: replace Abstract: Motivated by the Bures distance, we introduce a new family of distances, relative translation invariant Wasserstein distances, denoted by RW_p, as a
arXiv:2605.24003v1 Announce Type: cross Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data
arXiv:2605.24850v1 Announce Type: new Abstract: Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evalu
arXiv:2512.23995v2 Announce Type: replace-cross Abstract: Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To acc
arXiv:2605.25851v1 Announce Type: new Abstract: Embodied instruction following (EIF) requires agents to understand and execute complex natural language commands within interactive 3D environments. Des
arXiv:2605.24428v1 Announce Type: new Abstract: Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models
arXiv:2605.25151v1 Announce Type: new Abstract: Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms
arXiv:2605.25495v1 Announce Type: new Abstract: Robotic perception in unstructured environments remains challenging despite the zero-shot capabilities of foundation models such as SAM. This work attri
arXiv:2605.23940v1 Announce Type: new Abstract: How do multi-turn reasoning systems fail? The expected answer is logical contradiction, in which the system's maintained state becomes unsatisfiable. We
Cohere announced that Restock, their production-ready system, has reached a stable release milestone. The announcement indicates the technology is now available for enterprise deployment and real-worl
arXiv:2605.24251v1 Announce Type: new Abstract: Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods
arXiv:2605.25429v1 Announce Type: new Abstract: Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining. Nevertheless, existing approaches
arXiv:2605.24545v1 Announce Type: cross Abstract: Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches ma
Amid rapidly growing adoption of enterprise-level AI agents, there’s a disconnect emerging between ambition and execution. Although 85% of organizations say they want to be agentic within the next thr
arXiv:2605.26068v1 Announce Type: cross Abstract: Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these
arXiv:2605.25480v1 Announce Type: new Abstract: LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when ev
arXiv:2605.26019v1 Announce Type: cross Abstract: Online Terms of Service often function as contracts of adhesion, creating asymmetries that may expose consumers to potentially abusive clauses. In Chi
arXiv:2407.05682v2 Announce Type: replace Abstract: In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Re
arXiv:2605.26047v1 Announce Type: new Abstract: AI coding scaffolds like Claude Code and Codex use extit{retrying}: blocking actions flagged as risky and continuing the trajectory. We study retrying f
arXiv:2605.25111v1 Announce Type: new Abstract: Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing
arXiv:2602.02495v3 Announce Type: replace-cross Abstract: Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignmen
arXiv:2605.05795v2 Announce Type: replace Abstract: Decomposing complex tasks into a sequence of simpler subtasks can improve learning efficiency for an autonomous agent. Reinforcement learning (RL) c
arXiv:2510.25065v3 Announce Type: replace Abstract: Recent advances in sparse reward policy gradient methods have enabled effective reinforcement learning (RL)-based language model post-training. Howe
Ridiculously cool open source example using @LangChain_JS The Multi-Modal children’s bedtime story generator is an excellent example of LangChain streaming UI & stream namespace subscriptions - great
arXiv:2605.24113v1 Announce Type: new Abstract: Classical archetypal analysis is appealing for its interpretability, but its linear geometry can limit performance on data with strongly non-linear stru
arXiv:2605.24942v1 Announce Type: cross Abstract: Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation
arXiv:2605.23944v1 Announce Type: new Abstract: We model the interaction between a user and an AI driven recommendation system. The user initiates the process by conveying preference information throu
arXiv:2601.06201v2 Announce Type: replace-cross Abstract: Enterprises are confronted with an unprecedented escalation in cybersecurity vulnerabilities, with thousands of new CVEs disclosed each month.
arXiv:2605.24547v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This
arXiv:2605.24394v1 Announce Type: new Abstract: Robotic manipulation of deformable linear objects (DLOs) presents significant challenges due to complex dynamics and frequent self-occlusions. Existing
arXiv:2509.17057v3 Announce Type: replace Abstract: We present RoboManipBaselines, an open-source software framework for imitation learning research in robotic manipulation. The framework supports the
arXiv:2605.24475v1 Announce Type: cross Abstract: Trusted multi-view classification aims to deliver reliable fusion for accurate predictions and has recently attracted substantial attention in both ac
arXiv:2511.03963v2 Announce Type: replace-cross Abstract: We introduce a density-power weighted variant for the Stein operator, called the gamma-Stein operator. This is a novel class of operators deri
arXiv:2605.24721v1 Announce Type: new Abstract: The increasing use of automated translation quality estimation (QE) systems calls for practical, decision-oriented methods for evaluating their performa
arXiv:2605.25565v1 Announce Type: cross Abstract: While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting the
arXiv:2605.24817v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become an increasingly important paradigm for scaling Large Language Models (LLMs). As MoE models are incr
arXiv:2601.02144v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sp
arXiv:2605.24291v1 Announce Type: cross Abstract: We consider the conversion of musical recordings into human-readable sheet music annotated with timestamps. Such output lets a listener clearly visual
The NVIDIA RTX PRO 4500 accelerates genomic sequencing and drug discovery by slashing processing times. This professional desktop GPU features 32GB of ultra-fast GDDR7 memory and Blackwell architectur
arXiv:2605.24016v1 Announce Type: cross Abstract: Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is
arXiv:2605.25525v1 Announce Type: new Abstract: Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a centr
arXiv:2605.25984v1 Announce Type: cross Abstract: Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We presen
arXiv:2605.25546v1 Announce Type: new Abstract: Safety-critical control is essential for humanoid robots operating in complex human-centered environments, where physical safety constraints such as joi
arXiv:2601.21094v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safe
arXiv:2605.24270v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of mode
arXiv:2605.25492v1 Announce Type: new Abstract: Pairwise model comparisons drawn from foundation-model benchmarks ('A is safer than B') are read as quantitative verdicts but hinge on harness choices b